I realized the naivity of this remark shortly after I made it. There exists
a problem with the current implementation of clone, and a logical problem.
Firstly, if you create a thread with clone() it will not inherit the ioperms
of the parent, because it is zeroed out. Would it be possible to map the
io_bitmap of the parent into the chunk of memory that we need io_bitmap for?
You know, map a VM page over that? The other choice is to just do a bulk
copy of the parent's io_bitmap (fixing clone()) in the process. You could
take advantage of any highspeed bulk copies. The alternative is to grab
a page of memory that was previously zeroed out (can't the x86 do this in
hardware?) and just assume it's initialized.
--Perry
> >
> > i've attached the code that does the clone() latency measurement.
> >
> > -- mingo
> >
-- Perry Harrington Linux rules all OSes. APSoft () email: perry@apsoft.com Think Blue. /\- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu